Fully Funded PhD Studentship in AI for Early Detection of Neurodevelopmental Disorders (UK Home Applicants Only)
Project: Multimodal AI for Early Detection of Neurodevelopmental Disorders
Falcon Foundation Doctoral Programme in Collaboration with The University of Bedfordshire and Luton AI
A full-time, fully funded PhD studentship for UK Home students is available at the University of Bedfordshire to develop cutting-edge multimodal AI technologies that could transform the early detection of neurodevelopmental disorders and improve outcomes for children and families.
The studentship forms part of the Falcon FoundationDoctoral Programme, an initiative designed to widen access to doctoral study for talented individuals.
The successful candidate will also become part of Luton AI, the University of Bedfordshire’s applied AI ecosystem. Luton AI brings together academic research, specialist facilities, external partners and real-world projects to support the responsible development and practical application of artificial intelligence.
Through the Falcon Foundation Doctoral Programme, the studentship provides an annual stipend, full tuition fees, academic supervision, access to research infrastructure and specialist facilities, doctoral training, and wider researcher development support.
Falcon Foundation is a UK Charity no 1210094 registered with the Fundraising Regulator.
Funding
The studentship will provide:
- Full Home University tuition fees for three years – please note, this opportunity is only available to UK Home students.
- An annual stipend for up to three years.
- Access to specialist research facilities, computing infrastructure and doctoral training.
- Academic supervision and support from the University’s research community.
The stipend will be awarded annually for up to three years, subject to satisfactory academic progression and in accordance with the agreement with the Falcon Foundation.
Key dates
Closing date: Sunday 16 August 2026
Interview date: Virtual interviews will take place during the week commencing Monday 31 August 2026
Expected start date: October 2026
Study mode: Full-time
Duration: Three years, subject to satisfactory progression
The project
Early identification of neurodevelopmental disorders can enable children and families to access specialist assessment, intervention and support at an earlier stage. However, subtle neuromotor indicators can be difficult to identify reliably through visual observation alone.
This PhD project aims to develop cutting-edge multimodal AI system capable of analysing infant movements and identifying potential neurodevelopmental risks earlier than may be possible through existing clinical pathways.
The successful candidate will work closely with academic and clinical collaborators to support the collection, management and analysis of multimodal research data. The project will investigate the combined use of video and low-cost sensor technologies to capture subtle movement patterns, creating a rich dataset for AI-driven analysis.
Machine learning, deep learning, computer vision and multimodal AI methods will be used to identify clinically relevant indicators of neurodevelopmental risk. Depending on the direction of the research, the project may explore techniques such as convolutional neural networks (CNNs), Vision Transformers, multimodal transformer architectures, time-series analysis and explainable AI.
Explainable AI techniques will be incorporated to ensure that the system's outputs are transparent, interpretable and capable of supporting clinical decision-making.
The project builds directly on established research in infant motion analysis and explainable AI and benefits from existing collaborations with clinical partners in the UK and USA. These collaborations will provide opportunities to engage with multidisciplinary teams and contribute to research with real-world clinical impact.
The longer-term objective is to translate advanced AI research into a practical, affordable and accessible system that could support earlier assessment, guide clinical referrals and improve outcomes for children and their families.
Research environment
The successful candidate will undertake the project within the University of Bedfordshire’s growing artificial intelligence research and innovation environment and will be connected to the work of Luton AI.
Through Luton AI, the candidate will benefit from access to applied AI expertise, advanced computing infrastructure, specialist facilities and a wider network of academic, healthcare, public-sector and industry collaborators.
This environment will support the candidate in moving beyond the development of an AI model to consider responsible implementation, clinical relevance, explainability, user needs and the practical translation of research into real-world impact.
Engagement with the Falcon Foundation
The successful candidate will be expected to engage proactively and professionally with the Falcon Foundation throughout the PhD.
This will include:
- Providing appropriate updates on research progress and professional development.
- Participating in relevant Falcon Foundation activities, meetings and events.
- Sharing insights and outcomes from the research with the Foundation.
- Acting as a positive ambassador for the Falcon Foundation Doctoral Programme.
- Contributing, where appropriate, to the wider development and future impact of the programme.
The candidate should be willing to develop a positive and constructive relationship with the Falcon Foundation and demonstrate how the opportunity has supported their progression as a researcher.
Research objectives
The successful candidate will:
- Develop multimodal AI models for the early detection of neurodevelopmental risks.
- Investigate computer-vision methods for analysing infant movement and neuromotor patterns.
- Integrate video data with information collected through low-cost sensors.
- Develop explainable AI approaches that produce transparent and clinically meaningful outputs.
- Evaluate the reliability, accuracy and practical applicability of the proposed system.
- Work with academic and clinical collaborators to support the translation of the research into healthcare practice.
- Publish research findings in relevant peer-reviewed journals and conferences.
- Communicate research progress and outcomes to academic, clinical and non-specialist audiences.
Person specification
Qualifications
Applicants should normally have:
- A good honours degree, normally at least a UK 2:1 or international equivalent, in computer science, artificial intelligence, data science, biomedical engineering, electronic engineering or a closely related subject.
- A relevant master’s degree, or equivalent research or professional experience, would be advantageous.
Applicants with relevant professional or technical experience who can demonstrate their ability to undertake doctoral-level research may also be considered.
Knowledge
Applicants should demonstrate knowledge of one or more of the following areas:
- Artificial intelligence and machine learning.
- Computer vision and video analysis.
- Deep learning.
- Multimodal data analysis.
- Signal processing or sensor-data analysis.
- Explainable or responsible AI.
- Healthcare, biomedical or clinical data applications.
Knowledge of neurodevelopment, infant movement analysis or healthcare research would be beneficial but is not essential.
Experience
Experience in one or more of the following would be advantageous:
- Programming in Python or a comparable language.
- Using machine-learning frameworks such as PyTorch or TensorFlow.
- Working with image, video, time-series or sensor data.
- Designing and evaluating machine-learning models.
- Conducting quantitative research or statistical analysis.
- Working in multidisciplinary research environments.
- Preparing academic reports, technical documentation or research publications.
Skills and competencies
The successful candidate will be expected to demonstrate:
- A logical, analytical and methodical approach to problem-solving.
- The ability to plan and undertake research independently.
- Strong written and verbal communication skills.
- The ability to explain complex technical ideas clearly to specialist and non-specialist audiences.
- Careful research-data management and record-keeping.
- The ability to work effectively with academic, technical and clinical collaborators.
- An understanding of the ethical and responsible use of AI, particularly in healthcare.
- High levels of motivation, initiative and intellectual curiosity.
- The ability to manage competing priorities and work to agreed deadlines.
- A willingness to learn new technical and research methods.
- A willingness to engage proactively and professionally with the Falcon Foundation throughout the studentship.
Widening access to doctoral study
Applications are particularly encouraged from talented candidates who have the academic potential to succeed at doctoral level but who may previously have considered a PhD financially or practically inaccessible.
Selection will be based on applicants’ academic potential, relevant skills, research aptitude and ability to contribute to the proposed project.
Supervision and further information
The project will be supervised by:
Dr Massoud Khodadadzadeh
University of Bedfordshire
[email protected]
Dr Edward Braund
University of Bedfordshire
[email protected]
Prospective applicants are welcome to contact Dr Khodadadzadeh or Dr Braund for an informal discussion about the project before submitting an application.
How to apply
Applicants should submit:
- A completed University PhD application through the University’s Job portal
- A current curriculum vitae, including full details of all relevant degrees and qualifications.
- A personal statement explaining their interest in the project, relevant skills and experience, and suitability for doctoral study.
- A short, fully referenced survey of the relevant research field, approximately 750-1,500 (not including references) words in length. This should provide the academic background to the project, summarise current approaches to infant movement analysis and the early detection of neurodevelopmental disorders, and review relevant developments in computer vision, multimodal sensing, machine learning and explainable AI. The statement should identify key limitations or gaps in the existing literature and briefly explain how the proposed PhD research could address them. Applicants should use appropriate peer-reviewed academic sources and provide a complete reference list.
- Contact details for two academic or professional referees.
Please note that you may upload a maximum of two files. Each file must be no larger than 2 MB and must be in DOC, DOCX, PDF, RTF or TXT format.
Applications must be submitted by Sunday 16th August 2026.
The University of Bedfordshire, Luton AI and the Falcon Foundation are committed to widening participation in doctoral education and creating opportunities for talented researchers from a broad range of backgrounds.
